unsloth/DeepSeek-V3
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| Chatbot Arena | chat | 85.5 | high | | DeepSeek-V3 | **85.5** | **70.0** | | |
| MATH | math | 81.6 | Math | medium | | Math | GSM8K (EM) | 8-shot | 81.6 | 88.3 | 83.5 | **89.3** | |
| AlpacaEval | chat | 70.0 | high | | DeepSeek-V3 | **85.5** | **70.0** | |
none scraped.